Irfan Essa’s Academic Activities

Pei Yin, Irfan Essa, James Rehg, Thad Starner (2008) “Discriminative Feature Selection for Hidden Markov Models using Segmental Boosting”, ICASSP 2008 - March 30 - April 4, 2008 - Las Vegas, Nevada, U.S.A. (Paper: MLSP-P3.D8, Session: Pattern Recognition and Classification II, Time: Thursday, April 3, 15:30 - 17:30, Topic: Machine Learning for Signal Processing: Learning Theory and Modeling) (PDF|Project Site)

ABSTRACT

We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying feature selection techniques. Inspired by segmental k-means segmentation (SKS), we propose Segmentally Boosted HMMs (SBHMMs), where the state-optimized features are constructed in a segmental and discriminative manner. The contributions are twofold. First, we introduce a novel feature selection algorithm, where the temporal dynamics are decoupled from the static learning procedure by assuming that the sequential data are piecewise independent and identically distributed. Second, we show that the SBHMM consistently improves traditional HMM recognition in various domains. The reduction of error compared to traditional HMMs ranges from 17% to 70% in American Sign Language recognition, human gait identification, lip reading, and speech recognition.

Boosted audio-visual HMM for speech reading (IEEEXplore)

Yin, P. Essa, I. Rehg, J.M.
GVU Center, Georgia Inst. of Technol., Atlanta, GA, USA
This paper appears in: Signals, Systems and Computers, 2003. Conference Record of the Thirty-Seventh Asilomar Conference on
Publication Date: 9-12 Nov. 2003
Volume: 2
On page(s): 2013 - 2018 Vol.2
Number of Pages: 2361
ISSN:
ISBN: 0-7803-8104-1
INSPEC Accession Number:8555396
Digital Object Identifier: 10.1109/ACSSC.2003.1292334
Posted online: 2004-05-04 13:54:35.0
Abstract
We propose a new approach for combining acoustic and visual measurements to aid in recognizing lip shapes of a person speaking. Our method relies on computing the maximum likelihoods of (a) HMM used to model phonemes from the acoustic signal, and (b) HMM used to model visual features motions from video. One significant addition in this work is the dynamic analysis with features selected by AdaBoost, on the basis of their discriminant ability. This form of integration, leading to boosted HMM, permits AdaBoost to find the best features first, and then uses HMM to exploit dynamic information inherent in the signal.

Irfan A. Essa “Computers Seeing People”, AI Magazine 20(2): Summer 1999, 69-82

Abstract

AI researchers are interested in building intelligent machines that can interact with them as they interact with each other. Science fiction writers have given us these goals in the form of HAL in 2001: A Space Odyssey and Commander Data in Star Trek: The Next Generation. However, at present, our computers are deaf, dumb, and blind, almost unaware of the environment they are in and of the user who interacts with them. In this article, I present the current state of the art in machines that can see people, recognize them, determine their gaze, understand their facial expressions and hand gestures, and interpret their activities. I believe that by building machines with such abilities for perceiving, people will take us one step closer to building HAL and Commander Data.

Coding, analysis, interpretation, and recognition of facial expressions

Essa, I.A. Pentland, A.P. In IEEE Transactions on Pattern Analysis and Machine Intelligence, July 1997, Volume: 19 , Issue: 7, pp 757 - 763, ISSN: 0162-8828, CODEN: ITPIDJ. INSPEC Accession Number:5661539
Digital Object Identifier: 10.1109/34.598232

Abstract

We describe a computer vision system for observing facial motion by using an optimal estimation optical flow method coupled with geometric, physical and motion-based dynamic models describing the facial structure. Our method produces a reliable parametric representation of the face’s independent muscle action groups, as well as an accurate estimate of facial motion. Previous efforts at analysis of facial expression have been based on the facial action coding system (FACS), a representation developed in order to allow human psychologists to code expression from static pictures. To avoid use of this heuristic coding scheme, we have used our computer vision system to probabilistically characterize facial motion and muscle activation in an experimental population, thus deriving a new, more accurate, representation of human facial expressions that we call FACS . Finally, we show how this method can be used for coding, analysis, interpretation, and recognition of facial expressions

Daniel Goldman (1997 “Laugh and Your Computer Will Laugh With You, Someday” Jan 7, 1997 Issue, New York Times, Science Times

Quote from the article: “Emotions like fear, sadness and anger each announce themselves through a unique signature of changes in facial muscle, vocal inflection, physiological arousal, and other such cues. Building on techniques of pattern recognition already used for computer comprehension of words and images, Dr. Irfan Essa, a computer scientist at Georgia Tech, has constructed a computer system that can read people’s emotions from changes in their facial expression.”

Darrell, T.J.; Essa, I.A.; Pentland, A.P., “Task-specific gesture analysis in real-time using interpolated views” Transactions on Pattern Analysis and Machine Intelligence , vol.18, no.12, pp.1236-1242, Dec 1996
URL: [ieeexplore.ieee.org] [DOI]

Abstract

Hand and face gestures are modeled using an appearance-based approach in which patterns are represented as a vector of similarity scores to a set of view models defined in space and time. These view models are learned from examples using unsupervised clustering techniques. A supervised teaming paradigm is then used to interpolate view scores into a task-dependent coordinate system appropriate for recognition and control tasks. We apply this analysis to the problem of context-specific gesture interpolation and recognition, and demonstrate real-time systems which perform these tasks

International Conference on Face and Gesture Recognition (FG) 1996, October 13-16, 1996, Killington, Vermont

Alex Pentland (1996), “Smart Rooms”Scientific American, April 1996

Quote from the Article: “Facial expression is almost as important as identity. A teaching program, for example, should know if its students look bored. So once our smart room has found and identified someone’s face, it analyzes the expression. Yet another computer compares the facial motion the camera records with maps depicting the facial motions involved in making various expressions. Each expression, in fact, involves a unique collection of muscle movements. When you smile, you curl the corners of your mouth and lift certain parts of your forehead; when you fake a smile, though, you move only your mouth. In experiments conducted by scientist Irfan A. Essa and me, our system has correctly judged expressions-among a small group of subjects-98 percent of the time.”

Evan I. Schwartz (1995) “A Face of One’s Own | Memory, Emotions, & Decisions”, DISCOVER MagazineDecember 1, 1995.

Quote from the Article: “Chief among the members of his staff working on the problem is computer scientist Irfan Essa. To get computers to read facial expressions such as happiness or anger, Essa has designed three-dimensional animated models of common facial movements. His animated faces move according to biomedical data gathered from facial surgeons and anatomists. Essa uses this information to simulate exactly what happens when a person’s static, expressionless face, whose muscles are completely relaxed and free of stress, breaks out into a laugh or a frown or some other expression of emotion.”

Irfan Essa (1994), “Analysis, interpretation and synthesis of facial expressions“, PhD Thesis, MIT, Cambridge, MA, USA. (Advisor: Alex (Sandy) Pentland